Natural Language Processing II (SC674: Contents of Course
This document outlines the contents and reading list for a course on Natural Language Processing. The course covers basic theory and concepts in syntax, parsing, semantics, pragmatics, and NLP systems. It includes 39 hours of lectures on topics like phrase structure grammar, parsing algorithms, lexical semantics, and machine translation systems. Students will be evaluated based on midterm, final exams, homework assignments, and lecture participation.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0 ratings0% found this document useful (0 votes)
79 views4 pages
Natural Language Processing II (SC674: Contents of Course
This document outlines the contents and reading list for a course on Natural Language Processing. The course covers basic theory and concepts in syntax, parsing, semantics, pragmatics, and NLP systems. It includes 39 hours of lectures on topics like phrase structure grammar, parsing algorithms, lexical semantics, and machine translation systems. Students will be evaluated based on midterm, final exams, homework assignments, and lecture participation.
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4
Natural Language Processing II (SC674)
(Fourth revised version, 2002-2-25)
Prof. Feng Zhiwei
Contents of Course
Basic Theory of NLP (39 hours)
1 Introduction of NLP (1.5 hours)
1.0 What is NLP? 1.1 Main Domains of NLP 1.2 Brief History of NLP
2 Basic Concepts of Syntax (6 hours)
2.1 Phrase Structure Grammar (PSG) 2.2 PSG for English 2.2.1 Sentence Constructions of English 2.2.2 The Noun Phrase 2.2.3 Coordination 2.2.4 Agreement 2.2.5 Verb Phrase and Sub-categorization 2.2.6 Auxiliaries 2.2.7 Grammar Equivalent and Normal Form 2.2.8 Finite-State and Context-Free Grammar 2.2.9 Grammar and Human Processing
3 Parsing with PSG (4.5 hours)
3.1 Bottom-Up Parsing 3.2 Top-Down Parsing 3.3 Problems with Top-Down Parser 3.3.1 Left-recursion 3.3.2 Ambiguity 3.3.3 Repeated parsing of sub-trres 3.4 Some Algorithms 3.4.1 Earley algorithm 3.4.2 Finite-state parsing methods
4 Feature and Unification (3 hours)
4.1 Feature Structures in Grammar 4.2 Implementing Unification 4.3 Parsing with Unification Constraints 4.4 Types and Inheritance 5 Lexicalized and Probabilistic Parsing (3 hours) 5.1 Probabilistic Context-Free Grammar (PCFG) 5.2 Lexicalized PCFG 5.3 Human Parsing
6 Some Important Grammars in NLP (6 hours)
6.1 Category Grammar (CG) 6.2 Dependency Grammar (DG) and Valence Grammar (VG) 6.3 Linguistic String Theory (LST) 6.4 Link Grammar (LG) 6.5 Government and Binding theory (GB theory) 6.6 Functional Unification Grammar (FUG) 6.7 Generalized Phrase Structure Grammar (GPSG) 6.8 Head-Driven Phrase Structure Grammar (HPSG) 6.9 Definite Clause Grammar (DCG) 6.10 Montague Grammar (MG) 6.11 Conceptual Dependency Theory (CD theory)
7 Corpus Linguistics (6 hours)
7.1 Design and Development of Corpus 7.2 Pre-electric corpus 7.3 Types of electric corpus 7.4 Major electronic corpus 7.5 Corpus-based description of English 7.5.1 Lexical description 7.5.2 Grammatical study 7.5.3 Corpus Analysis 7.5.4 Corpus annotation 7.5.5 Procedures used in corpus analysis 7.6 Corpus Linguistics and NLP
8 Semantics (4.5 hours)
8.1 Representing Meaning 8.1.1 Predicate-Argument Structure 8.1.2 First Order Predicate Calculus 8.1.3 Some Linguistically Relevant Concepts 8.1.4 Alternative Approaches to Meaning 8.2 Semantic Analysis 8.2.1 Syntax-Driven Semantic Analysis 8.2.2 Robust Semantic Analysis 8.3 Lexical Semantics 8.3.1 Relations among lexemes and their senses 8.3.2 The internal Structure of Words 8.4 Word Sense Disambiguation and Information Retrieval 8.4.1 Selectional Restriction-Based Disambiguation 8.4.2 Robust Words Sense Disambiguation 8.4.3 Information Retrieval
9 Pragmatics (4.5 hours)
9.1 Discourse 9.2 Dialogue and Conversational Agents 9.3 Natural Language Generation
NLP systems (6 hours)
10 NLU (Natural Language Understanding) Systems (3 hours)
10.1 Early NLU systems 10.2 LUNAR 10.3 SHRDLU 10.4 MARGIE (Meaning Analysis, Response Generation and Inference on English) 10.5 SAM (Script Applier Mechanism) 10.6 PAM (Plan Applier Mechanism) 10.7 TALE-SPIN 10.8 POLITICS 10.9 LIFER
[1] R. Hausser, Foundations of Computational Linguistics (man-machine communication in natural language), Springer-Verlag, 1999. [2] G. Gazdar, Ch. Melish, Natural Language Processing in LISP, Addison-Wesley Publishing Company, 1989. [3] T. Winograd, Language as a Cognitive Process, Vol.1: Syntax, Addison-Wesley, 1983. [4] R. Grishman, Computational Linguistics, Cambridge Univ. Press, 1986. [5] Arturo Trujillo, Translation Engines: Techniques for Machine Translation, Springer, 1999. [6] Peter Whitelock & Kieran Kilby, Linguistic and Computational Techniques in Machine Translation System Design, UCL Press, 1995. [7] R. Schank, C. K. Reisbeck, Inside Computer Understanding: five programs plus miniatures, Lawrence Erlbaum Associates, Inc., 1981. [8] G. Kennedy, Introduction to Corpus Linguistics, Addison Wesley Longman Limited, 1998. [9] Feng Zhiwei, Fundamentals of Computational Linguistics, Commercial Press, Beijing, 2001. [10] Feng Zhiwei, Natural Language Processing by Computer, Foreign Language Education Press, Shanghai, 1996. [11] D. Jurafsky, J. Martin, Speech and Language Processing, Prentice Hall Inc., 2000 [12] B. Manaris, Natural Language Processing: A Human-Computer Interaction Perspective, Advances in Computers, Volume 47, p1-p66), Academic Press, San Diego, 1998. [13] J. Allen, Natural Language Understanding, 2nd edn, Benjamin/Cummings, Redwood City, California, 1994. Grading policy Mid examination: 30% Final examination: 40% Homework: 20% Lecture participation: 10%